Abstract: The disclosure relates to a method for controlling a robot to return to a base. The method includes the robot receives a return-to-base control signal; the robot walks along different preset paths according to different receiving conditions of guidance signals; and when detecting an intermediate signal during walking along a preset path, the robot returns to the base directly under piloting of the intermediate signal instead of walking along the preset path. The guidance signals are signals sent by a charging base, for piloting the robot to return to the base, and include the intermediate signal.

Abstract: The invention discloses a method for robots to improve the accuracy of an obstacle labeling, which comprises: making two positionings according to set moments, and then acquiring positioning poses of the two positionings on a grid map respectively at a first moment and a second moment; defining coverage areas of the first and the second moments according to positions of the two positionings, acquiring confidence coefficients of the two positionings, and processing the coverage areas through the confidence coefficients; interpolating the positioning poses, and constructing a closed graph according to the positioning poses, the pose interpolation, and the processed coverage areas; and obtaining a grid occupied by the closed graph on the grid map and modifying the obstacle labeling according to the grid occupied by the closed graph on the grid map and the area of the closed graph.

Abstract: The present invention relates to grid and voxel positioning methods based on a laser observation direction, a robot, and a chip. The grid positioning method comprises: selecting two preset intersection points that are in a same preset grid in which a laser point is located; then, in the two preset intersection points, setting the preset intersection point farthest from an observation point as a first preset intersection point, and setting the preset intersection point closest to the same observation point as a second preset intersection point; and according to a magnitude relationship between a ratio of a second preset distance to a first preset distance and a preset proportion coefficient, determining a target grid hit by the laser point in the direction of an observation ray, so as to form a latest hit grid position of the laser point within the two-dimensional grid map.

Abstract: The disclosure discloses a method for building a local point cloud map and a visual robot. According to the method for building the local point cloud map, point clouds which reflect a position of a large-range region around a robot are sampled according to a preset salient pose change condition; point clouds at different height positions are described in the form of a 3d histogram.

Abstract: Disclosed are a method for dividing a robot area based on boundaries, a chip and a robot. The method includes: setting, when the robot travels along the boundaries in a preset boundary direction in an indoor working area, a reference division boundary line according to data scanned by a laser sensor of the robot in real time; and identifying, after the robot finishes traveling along the boundaries in the preset boundary direction, a door at a position of the reference division boundary line according to image characteristic information of the position of the reference division boundary line acquired by a camera of the robot, and marking the reference division boundary line on a laser map, so as to divide the indoor working area into different room subareas by means of the door.

Abstract: The present disclosure provides a method for expanding a working area based on a laser map, a chip and a robot, and the method for expanding the working area includes using map pixel point information obtained by laser scanning to position pending boundary lines, deciding a next expansion of a rectangular working area according to an increment of a diagonal length of the rectangular working area framed by the pending boundary lines in a current expansion process, stopping expanding the rectangular working area of the robot when the increment of the diagonal length before expanding and after expanding reaches an overlap condition.

Abstract: A method for correcting a determination threshold of a floor medium and a method of detecting thereof are provided. The method is used for controlling a mobile robot equipped with a sound emitter and a sound receiver to detect and recognize the floor medium during a movement just started. A first detection result of a current floor medium is obtained by actively transmitting and receiving a sound signal, then, a to-be-adjusted detection result of the current floor medium is obtained only by passively receiving the sound signal through the sound receiver, and according to the similarity/difference of the two detection results, the determination threshold is corrected in the case of passively receiving the sound signal, so that the to-be-adjusted detection result is determined to be consistent with the first detection result.

Abstract: An edgewise path selection method for robot obstacle crossing, a chip, and a robot. The method includes: first, planning an edgewise prediction paths for the robot obstacle crossing, and selecting, on a navigation path which is preset, preset inflection points satisfying a guide condition, and the navigation path formed by connecting inflection points is preset for the robot; the inflection points are used for guiding the robot to move to a final navigation target point; then according to information of distances between all the edgewise behavior points on each of the edgewise prediction path, and the preset inflection points satisfying the guide condition on one same navigation path, selecting one edgewise prediction path having a minimum deviation degree relative to the navigation path, so that the robot walks in an edgewise direction of the edgewise prediction path which is selected after colliding with an obstacle.

Abstract: A method for determining a termination of an obstacle-crossing, a method for controlling an obstacle-crossing control, a chip, and a robot. The obstacle-crossing termination determination method includes: when a robot walks along an edge according to a pre-planned shortest predicted path along the edge, selecting a second preset inflection point set, which meets a guiding condition, from a preset navigation path; an optimal inflection point is acquired from the second preset inflection point set, which meets the guiding condition; whether an obstacle is marked on a line segment which connects the optimal inflection point to the current position of the robot is determined; if so, the current obstacle crossing performed by the robot is not determined to be terminated; otherwise, the current obstacle crossing performed by the robot is determined to be terminated.

Abstract: A recharging control method of a desktop robot is provided. The desktop robot includes a robot body provided with a camera and a base. The recharging control method includes the following steps.

Abstract: A method for preventing a robot from colliding with a charging base, including: step 1, during a process of moving in a current working area of the robot, detecting, in real time, a reception condition of a base avoidance signal of the robot within a received signal coverage range thereof; and step 2, establishing a safety area in the current working area according to a direction feature relationship between the base avoidance signal and a preset working path of the robot, and before establishing the safety area, according to an orientation relationship between the base avoidance signal and a direction of a current moving path of the robot, marking and establishing a danger area at a position that satisfies a collision avoidance relationship with a current position of the robot, so that the robot avoids the charging base during the process of moving in the current working area.

Abstract: An automatic generation method for a robot return-to-base code includes the following steps that: on the basis of a preset signal collection mode, a robot collects a guide signal which is sent by a charging base and distributed within a preset range (S1); the robot transmits signal information and position information of the robot recorded when the guide signal is collected to a data processing device (S2); and the data processing device generates a robot return-to-base code corresponding to the charging base according to the received signal information and position information (S3). By means of the information collected by the robot in different modes, the data processing device automatically generates, according to the information, the robot return-to-base code corresponding to the charging base, so that research and development personnel do not need to delve into a robot return-to-base algorithm or write a specific return-to-base code.

Abstract: The disclosure relates to a system for locating a charging base of a self-moving robot and method for locating a charging base of a self-moving robot. A position of the charging base can estimated according to a charging base locating area constructed when the self-moving robot receives infrared signals of the charging base, meanwhile, the position of the charging base which is estimated can be continuously adjusted according to a relationship between the charging base locating area and infrared signal receivers when the infrared signals are received in the subsequent motion process of the self-moving robot.

Abstract: Disclosed are an area cleaning planning method for robot walking along the boundary, a chip and a robot. The area cleaning planning method includes: on a laser map which is scanned and constructed by a robot in real time, the robot is controlled to walk along the boundary in a predefined cleaning area framed at the current planning starting point position, so that the robot does not cross out the predefined cleaning area in the process of walking along the boundary; meanwhile, according to the division condition of the room cleaning subareas that conform to the preset wall environment condition in the predefined cleaning area, the robot is controlled to walk along the boundary in a matched area, when the robot walks along the boundary in the matched area and returns to the planning starting point position, the robot is controlled to perform planned cleaning in the matched area.

Abstract: A method for a robot to judge whether the robot collides with a virtual wall, and a chip and the intelligent robot. The method comprises: providing pre-judgement regions on two sides of a virtual wall, so that when entering the pre-judgement regions, the robot can judge whether the robot collides with the virtual wall by combining a current direction of the robot as well as a relationship between a straight-line distance from the robot to a reference point and a straight-line distance from the reference point to a center point of the virtual wall.

Abstract: An interpolation filtering system implemented by a digital circuit is provided, it includes an interpolation filtering operation controller, a cascaded drive module, an intermediate result cache Random Access Memory (RAM), and a filter coefficient storage Read Only Memory (ROM). The intermediate result cache RAM is configured to store externally input data of the interpolation filtering system and intermediate results output by the filter operation modules. The filter coefficient storage ROM is configured to store filter coefficients required for calculation by the filter operation modules.

Abstract: A method and system for path sweeping of a cleaning robot, and a chip are disclosed. The method includes: detecting, in real time, a collision state of the cleaning robot in a turning process during S-shaped sweeping in a current cleaning area; and then controlling an -shaped path of the cleaning robot according to the collision state, so that the cleaning robot achieves sweeping an area between an arc-shaped edge corresponding to a turning part of the -shaped path, and a corner of the current cleaning area.

Abstract: The present disclosure relates to a method for straight edge detection by a robot and a method for reference wall edge selection by a cleaning robot. The method for straight edge detection by the robot includes that: position coordinates of detection points are determined according to distance values detected by a distance sensor of the robot and angle values detected by an angle sensor of the robot, and then a final straight edge is determined according to a slope of a straight line formed by adjacent two of the detection points.

Abstract: The disclosure discloses a control device for a robot to tease a pet and a mobile robot. The primary sensor is configured to continuously collect a preset number of frames of pet motion images in each motion cycle. The state recognizer is configured to judge the matching between the pet motion images continuously collected by the primary sensor and a pre-stored digital image of pet behavior, and then parse a matching result into behavior state parameters of a pet. The behavior interferometer is configured to adjust and control a behavior state of the pet according to the behavior state parameters and an additional road sign image provided by the secondary sensor. The laser projector is configured to project a laser beam to form a structural light spot, so that the pet changes toward the behavior state adjusted by the behavior interferometer.

Abstract: The disclosure discloses a historical map utilization method based on a vision robot, including: S1, the vision robot is controlled to continuously collect image of a preset road sign of a preset working area, and road sign information of the preset road sign is obtained; S2, the obtained road sign information is transmitted to a first map positioning system and a second map positioning system; S3, the first map positioning system and the second map positioning system are controlled to respectively process corresponding road sign information, thereby obtaining first pose information and second pose information; S4, the first pose information and the second pose information under the same preset road sign are selected, and a transformation relationship formula of the first pose information and the second pose information is calculated; and S5, the historical map is controlled to perform a corresponding transformation operation, and subsequent motion control is performed.